Search Results (1,098)

Ultra-High Molecular Weight Polyethylene (UHMWPE), the standard base material in ski manufacturing, offers excellent gliding performance but exhibits limited mechanical and scratch resistance on hard and icy snow conditions. In this work, stainless steel is proposed as a mechanically robust alternative, and its inherently higher friction against snow is addressed through surface engineering. The snow friction behavior of 301H stainless steel surfaces decorated with fishbone-like microstructures combined with Laser-Induced Periodic Surface Structures (LIPSSs) was investigated using a custom-built snow tribometer. Several pattern designs, with different pitch distances and depths, were engraved using femtosecond laser pulse irradiation. We conducted morphological, physical, and chemical investigations through microscopy, static contact angle measurements, and X-ray Photoelectron Spectroscopy analyses. Results indicate that the gliding performance is not directly related to the modifications in surface chemistry and wetting behavior of the samples but is affected by the geometry and orientation with respect to the sliding direction of the specific micro- and nano-features. Overall, we achieved friction coefficient values comparable to those found in UHMWPE with a fast and economically sustainable single-step laser-texturing process. This approach allows the industrial up-scaling of the fishbone-texture design to real-size alpine ski prototypes. Full article

In complex low-altitude environments, unmanned aerial vehicles (UAVs) require reliable positioning, yet Global Navigation Satellite System (GNSS) signals are vulnerable to occlusion and interference. Pseudolite-augmented cooperative localization, which combines ground base-station signals with inter-UAV relative observations, can complement GNSS in such environments. However, two practical issues remain in real-world deployment: UAV-to-base-station (U-B) and UAV-to-UAV (U-U) observations have markedly different error statistics that a unified noise adjustment cannot handle, and the conservative covariance estimates produced by Covariance Intersection (CI) fusion bias the innovation-based adaptive noise estimation in distributed architectures. To address these issues, this paper proposes a Distributed Group Covariance Compensation Adaptive Kalman Filter (DGCC-AKF) for collaborative enhancement of UAV regional localization. DGCC-AKF establishes a group adaptive mechanism that independently adjusts the noise covariance matrices of U-B and U-U observations, enabling observation-type-level adaptive weighting that suppresses anomalous U-B or U-U measurements at the group level. In addition, a bounded covariance compensation factor is incorporated to alleviate the CI-induced conservatism in the adaptive noise estimation. The proposed method is evaluated on a 2800 km² semi-physical testbed based on the Ground-based High-precision Local Positioning System (GH-LPS) pseudolite network using measured U-B observations and high-dynamic (>300 km/h) flight trajectories collected from a fixed-wing platform across three independent flight sessions. Results demonstrate that under observation fault periods, the proposed method improves 3D positioning accuracy by up to about 75% over single-UAV extended Kalman filter (EKF). Compared with two advanced algorithms in this field, variational Bayesian adaptive Kalman filter (VBAKF) and maximum correntropy criterion Kalman filter (MCC-EKF), it is the only scheme that remains accurate and stable across all UAVs and fault types. The framework provides a practical step toward field deployment for resilient multi-UAV cooperative navigation in pseudolite-augmented GNSS-denied regions. Full article

Remote tower operations require air traffic controllers to maintain continuous visual monitoring and integrate information from panoramic displays, radar data, flight strips, and voice communication. Such screen-mediated and sustained surveillance tasks may lead to covert fatigue, which is difficult to capture using a single physiological or behavioral signal. To address this issue, this study proposes a Gated EEG–Eye Fusion Network (GEEF-Net) for window-level fatigue detection in remote tower controllers. EEG and eye-tracking signals were synchronously collected during simulated remote tower tasks and segmented into 5 s windows with a 2 s step. For each window, 53 EEG features and 47 eye-tracking features were extracted to construct a 100-dimensional multimodal representation. GEEF-Net adopts a lightweight modality-gating mechanism to adaptively weight EEG and eye-tracking representations before fatigue classification. Under the main subject-dependent validation setting, GEEF-Net achieved an Accuracy of 0.883, an F1-score of 0.788, and a ROC-AUC of 0.944, outperforming EEG-only, eye-only, and early-fusion baselines in most overall metrics. The gating analysis indicated that eye-tracking features received a higher average weight than EEG features, suggesting the importance of visual behavior in remote tower fatigue detection. Cross-subject validation showed that individual differences remain a major challenge, while few-shot subject-specific calibration improved model adaptation when limited target-subject samples were available. These findings suggest that EEG–eye-tracking fusion with lightweight modality gating is a feasible approach for fatigue detection in simulated remote tower tasks. However, larger datasets and operationally realistic validation considering shift work, circadian effects, and operational pressure are still required before the approach can be considered operationally reliable. Full article

This study examines how energy market uncertainty affects corporate financial stability and whether environmental, social, and governance (ESG) performance mitigates this relationship. Using a panel of 168 non-financial Australian firms from 2011 to 2023, we employ a two-step system generalized method of moments (GMM) with extensive robustness checks. The results reveal three central findings. First, energy market uncertainty exerts a statistically significant and economically meaningful negative effect on corporate financial stability, indicating that heightened energy price volatility amplifies firms’ financial fragility. Second, ESG performance is positively associated with financial stability, suggesting that sustainability-oriented firms exhibit superior risk management and resilience. Third, ESG performance significantly attenuates the adverse impact of energy market uncertainty, providing strong evidence that ESG functions as an effective shock-absorbing mechanism. These findings are robust to alternative measures of financial stability and energy uncertainty, different lag structures, alternative estimation methods, and a wide range of subsample analyses. Further analyses show that the moderating role of ESG is not driven by a single pillar; rather, environmental, social, and governance dimensions jointly enhance firms’ capacity to withstand energy-related shocks. The buffering effect of ESG is stronger among high-ESG firms, in knowledge- and technology-intensive sectors, and during periods of heightened systemic stress such as the COVID-19 pandemic. Overall, the study provides novel firm-level evidence that ESG performance enhances corporate resilience to energy market uncertainty. The findings have important implications for policymakers, investors, and corporate managers seeking to strengthen financial stability in an era of elevated energy volatility and accelerating sustainability transitions. Full article

Accurate Unmanned Aerial Vehicle (UAV) position estimation is the cornerstone of urban low-altitude safety management systems. Time Difference of Arrival (TDOA) and Remote Identification (Remote ID) are widely used surveillance technologies with complementary characteristics. TDOA provides high-rate updates but suffers from geometry-induced horizontal–vertical anisotropy and multipath effects, while Remote ID supplies absolute state information yet struggles with intermittent sampling and packet loss. Existing fusion schemes typically address these issues in isolation: sequential filtering manages asynchrony but assumes Gaussian noise, robust estimators suppress outliers at the cost of discarding valid data, and coupled-filter architectures allow vertical anomalies to contaminate horizontal estimates through the Kalman gain cross-coupling. No prior framework jointly handles structural TDOA altitude jumps, stochastic Remote ID timing jitter, and the geometric anisotropy between estimation subspaces within a single coherent pipeline. To bridge this gap, we propose a Hybrid Conditional Kalman Filter (HCKF) framework comprising three integrated modules. First, a kinematics-based temporal alignment module maps asynchronous measurements onto a uniform timeline and predicts missing samples, resolving cross-modal time mismatches. Second, a measurement quality evaluation mechanism detects TDOA altitude steps via robust two-layer stratification and scores Remote ID timing irregularity through a confidence mapping, converting these anomalies into dynamic covariance adjustments and weight caps without discarding observations. Third, a Subspace-Decoupled Fusion strategy exploits the physical insight that TDOA horizontal precision derives from hyperbolic intersection geometry, whereas its vertical estimates suffer from weak observability due to near-coplanar ground-station deployment . By applying entropy-guided weighting in the horizontal plane and a conditional Remote ID-dominant rule in the vertical axis, this design prevents cross-dimensional error propagation. The framework was validated using three real-world flight missions at distinct altitudes (255 m, 345 m, and 440 m) totaling 13.51 km of flight distance, with RTK serving as ground truth. HCKF reduces the Root Mean Square Error by over 40% relative to single-source baselines (95% bootstrap confidence interval: [35.2%, 48.7%]), and paired Wilcoxon signed-rank tests confirm statistically significant improvement ($p<0.01$) over standard EKF, Covariance Intersection, and Iterative CI across all three tracks. Full article

Accurate prediction of pile-cap strain is crucial for the safety of wind-turbine foundations, yet conventional methods struggle to screen key features from high-dimensional monitoring data and to model the nonlinear coupling between endogenous and exogenous variables, hindering both accuracy and interpretability. To address these limitations, this paper proposes a pile-cap-strain prediction method integrating XGBoost-SHAP feature selection with the TimeXer deep-learning model. XGBoost-SHAP first identifies critical predictors from high-dimensional pile-stress data; the TimeXer model then exploits its endogenous–exogenous fusion mechanism for strain prediction. The results show that XGBoost-SHAP effectively selected 10 key features, of which the upper-middle and middle windward-side stresses (Z1-4A, Z1-5A) contributed over 40% of the explanatory power. This stage performs dimensionality reduction and sensor-importance interpretation, halving the input dimensionality while maintaining accuracy comparable to the full 19-channel input. TimeXer achieved a coefficient of determination (R²) of 0.993 in single-step prediction, comparable to the best-performing baselines, and maintained stable performance over a 120 min multi-step horizon. In a zero-shot cross-site transfer test, TimeXer attained the highest eight-step average R² (0.914) among all models, indicating strong cross-site generalization. Attention-mechanism visualization further suggested consistency between the model’s prediction logic and structural mechanics principles. The proposed framework provides a technical solution combining high accuracy with strong interpretability for wind-turbine foundation health monitoring. Full article

Flexible strain sensors have attracted considerable attention in gait recognition owing to their ability to adhere directly to the skin near joints and transduce local deformation. In existing work, however, sensor placement and orientation are largely determined by anatomical experience, while multi-channel classification still relies on back-end digital processors, whose power consumption and latency constrain system practicality in wearable scenarios. This paper presents an integrated design path that proceeds from skin-mechanics theory through sensor-layout optimization to analog-domain front-end inference. On the layout side, the lines-of-non-extension (LoNE) theory is employed to convert the selection of sensor attachment angles from empirical judgment into a calculable mechanics problem; guided by the spatial course of LoNE in the ankle and knee regions, the positions and angles of the nine sensors are determined individually—channels perpendicular to the LoNE capture maximum strain, channels offset by 45 degrees supplement non-sagittal-plane information, and a channel aligned along the LoNE provides a near-zero-strain reference. On the circuit side, the mathematical equivalence between the weighted summation of a linear classifier and Kirchhoff’s current law (KCL) nodal current superposition is exploited to map the classification operation onto current aggregation in an analog circuit, yielding an in-sensor computing (ISC) front end in which the nine-channel weighted summation is completed in a single analog step. The sensors are fabricated by screen-printing a liquid-metal–polymer composite conductive ink onto a TPU film substrate, with a gauge factor RSD of $6.8\%$ and a tensile linearity $R^2>0.99$. Using walking, running, and stair descent as verification targets, the analog classifier reaches 99% accuracy at the circuit-level functional-verification stage. On real multi-subject data, it achieves $87.0\%\pm 8.4\%$ accuracy under intra-subject cross-session validation, with an analog-domain inference response faster than $100\mathsf{\mu }\mathrm{s}$. This design path is not bound to a specific joint or sensor material; when the layout methodology is extended to additional joint regions and the circuit architecture incorporates multiple outputs to cover more classification categories, the same workflow remains applicable, offering a promising low-power, lightweight technical solution for wearable motion monitoring. Full article

The utilization of existing telecommunication infrastructure for environmental monitoring via opportunistic sensing is rapidly advancing the field of distributed fiber optic sensing (DFOS). However, while custom-engineered sensing cables are highly characterized for hydrostatic pressure, the complex mechanical response of standard armored telecommunication networks remains largely unquantified. This study experimentally investigates the non-linear distributed pressure sensitivity of three commercial telecommunication cables (Anti-Rodent, Duct, and Microcable) across a hydrostatic pressure range of 0 to 800 PSI. Measurements were conducted using Tunable Wavelength Coherent Optical Time Domain Reflectometry (TW-COTDR) with a 20 cm spatial resolution, utilizing a stepped depressurization protocol with 15-min stabilization holds to isolate true steady-state longitudinal strain. The results reveal that protective cable armoring induces severe mechanical non-linearity. The rigid Glass Reinforced Plastic (GRP) rods of the Anti-Rodent cable acted as a structural vault at low pressures before yielding to become highly sensitive above 400 PSI. Conversely, the corrugated steel tape of the Duct cable exhibited high initial sensitivity followed by mechanical stiffening, while the unarmored Microcable maintained a linear response. These findings establish that a single linear calibration coefficient is invalid for heavily armored infrastructure, highlighting the critical need for structural characterization prior to opportunistic field deployments. Full article

The zig-zag eel (Mastacembelus armatus) exhibits sexual dimorphism in growth patterns. Identifying the genes involved in sex differentiation is a crucial step toward achieving single-sex breeding and serves as a vital foundation for elucidating the XY sex determination mechanism in M. armatus. This study measured the morphological characteristics of male and female M. armatus and found that males were significantly superior to females in body weight and nearly all morphological indices. Subsequently, whole-transcriptome sequencing was performed on the gonads of adult males and females, identifying 11,714 DEmRNAs, 3442 DElncRNAs, 416 DEcircRNAs, and 620 DEmiRNAs, including male sex differentiation genes such as Sox30, Tbx1, Sox9, and Gata4, and female sex differentiation genes like Sox3, Foxl2, and Wnt4a. Functional enrichment analysis identified pathways associated with sex differentiation, including the TGF-beta signaling pathway, the steroid hormone biosynthesis, the Hippo signaling pathway, and the Wnt signaling pathway, etc. A ceRNA network was constructed based on differentially expressed mRNAs and ncRNAs, revealing that the sex differentiation-related genes Sox3, Sox9, Sox30, Tbx1, and Wt1 are regulated by one or multiple pairs of lncRNA/circRNA-miRNA pairs. The study results will provide molecular targets for research on sex-controlled breeding in M. armatus and lay an important theoretical foundation for clarifying its sex differentiation mechanisms. Full article

The 5G Wireless and Wireline Convergence (5G-WWC) standards introduce critical network functions—notably the Access Gateway Function (AGF) and the User Plane Function (UPF)—to enable unified wired and wireless access through a single 5G core. However, deploying and integrating these functions across heterogeneous programmable hardware platforms remains a significant open architectural challenge. This paper presents a configurable integration framework that orchestrates AGF and UPF workloads on heterogeneous programmable data planes, specifically NVIDIA BlueField-2 Data Processing Units (DPUs) and P4-based switches. Unlike traditional, hardware-specific implementations, the framework provides a unified control plane that dynamically manages AGF-only, UPF-only, or Combined AGF/UPF deployments. A hardware abstraction mechanism decouples the control logic from pipeline-specific details, enabling the same control plane to drive different underlying hardware without modification. A Generic Flow Rule interface standardises communication between the control plane and each user-plane backend, while a merged DPU pipeline for Combined AGF/UPF eliminates the redundant GTP-U encapsulation and decapsulation steps inherent in a naively cascaded design. Experiments on NVIDIA BlueField-2 DPUs achieve near-100 Gbps throughput across all three TR-470 scenarios (AGF-only, UPF-only, and Collocated AGF/UPF). The Combined AGF/UPF configuration exhibits lower end-to-end latency than the separated AGF + UPF configuration, confirming both the feasibility and the efficiency of the proposed framework for next-generation high-performance programmable networks. Full article

We derive the charged-lepton mass chain from the Recognition Composition Law (RCL) together with normalization, curvature normalization, and standard regularity. Through the theorem chain Tr1–Tr8, these postulates fix the golden ratio $\phi = \left(1+\sqrt{5}\right)/2$, the minimal period T_min = 8, the selected dimension D = 3, and the cube integers entering the master mass law. The charged-lepton formula is then assembled from the coherence scale, the lepton-sector baseline, the charge correction, and the derived generation steps. All parameters are discrete structural inputs, integers from cube geometry, named symmetry factors, and one external mathematical constant, rather than continuously adjustable dials. The construction is a structural constraint on the effective charged-lepton flavor pattern, not a replacement for the electroweak Higgs mechanism or for the full Standard Model quantum field theory. At the conversion stage to the International System of Units (SI), the electron fixes the single calibration anchor ${\tau }_0$, while the fine-structure constant $\alpha$ enters only as a fixed external dimensionless constant in the refinement layer. The phrase “zero continuously adjustable parameters” refers to the dimensionless content of the framework: the anchor ${\tau }_0$ is a unit-scale calibration fixed by the measured electron mass and cancels identically from every charged-lepton mass ratio. With that one anchor set, the remaining charged leptons become forward predictions: $m_{\mu }\in \left(\mathrm{105.5,105.9}\right) \mathrm{M}\mathrm{e}\mathrm{V}$ and $m_{\tau }\in \left(\mathrm{1774,1779}\right) \mathrm{M}\mathrm{e}\mathrm{V}$, with relative errors below $0.3\%$ and $0.2\%$, respectively. Floating-point evaluation gives $m_{\mu }\approx 105.658 \mathrm{M}\mathrm{e}\mathrm{V}$ and $m_{\tau }\approx 1776.71 \mathrm{M}\mathrm{e}\mathrm{V}$. Full article

Background/Objectives: Metabolic dysfunction-associated steatotic liver disease (MASLD) is a systemic disorder driven by genetic predisposition, epigenetic programming, metabolic rewiring, and immune dysregulation. Although population genetics and single-cell transcriptomics have advanced our understanding, the multi-omic causal architecture of MASLD at cellular resolution remains poorly defined. This study aimed to establish an integrative framework linking genetic causality to cell-type-specific tissue dysfunction. Methods: Multi-layered Mendelian randomization (MR) and summary-data-based MR (SMR) across large-scale eQTL and pQTL datasets were applied to prioritize causal genes. Single-cell eQTL-based MR across 14 immune lineages generated cell-type-specific causal hypotheses, which were validated using human hepatic single-cell RNA-sequencing data (GSE136103). Two-step mediation MR quantified upstream epigenetic and downstream metabolic mechanisms. A high-fat diet (HFD)-induced murine model provided organismal validation. Results: Multi-layered MR nominated PLXND1 as a robust causal driver of MASLD. Single-cell eQTL-based MR revealed a functional dichotomy: PLXND1 upregulation in CD8⁺ effector memory T-cells decreased MASLD risk (OR = 0.486, 95% CI: 0.290–0.813, p = 0.006), whereas upregulation in natural killer cells (OR = 1.567, 95% CI: 1.337–1.837, p < 0.001), non-classical monocytes, and dendritic cells increased risk. Human hepatic single-cell transcriptomics confirmed that PLXND1 marks an anti-fibrotic, IFNG-high CD8⁺ T subset and a pro-inflammatory lipid-associated macrophage (LAM) population. Mediation MR identified DNA methylation at cg26767922 and cg08471739 as protective mediators acting predominantly via PLXND1 downregulation (92.39% and 64.50% mediation, respectively), and linked PLXND1 to six circulating metabolites. HFD mice showed significant hepatic PLXND1 upregulation. Conclusions:PLXND1 functions as a lineage-dependent molecular switch in MASLD, validated across genetic, epigenetic, metabolic, and single-cell dimensions. These findings caution against systemic PLXND1 blockade and support precision therapeutic strategies targeting hepatic innate immune cells. Full article

Currently, there is no existing methodology within commercially available software packages for accurately simulating the gradual evaporation of the aqueous phase in batch thermomechanical dehydration processes involving highly stable water-hydrocarbon emulsions. This limitation constitutes a significant obstacle to the widespread industrial implementation of a promising approach for liquid hydrocarbon waste disposal, which relies on the evaporation of the aqueous phase under intensive stirring conditions, ultimately producing a hydrocarbon product with residual water content. In this study, the widely used Aspen HYSYS V12 software was employed to model these processes. The primary objective was to identify the most appropriate thermodynamic model accurately describing vapor–liquid phase transitions during the boiling of the aqueous phase in highly stable water–hydrocarbon emulsions, with water content ranging from 2 to 60% by weight. The modeling of the gradual boiling process was divided into several sequential stages, each representing a single evaporation step. The initial feedstock temperature was set at 90 °C, with subsequent stages involving temperature increments of 5 °C until the residual water content in the product fell below 0.5% by weight. Four thermodynamic models were evaluated for their ability to predict phase equilibria: Peng–Robinson, Wilson, UNIQUAC, and NRTL. It was observed that the Peng–Robinson model poorly describes the dehydration process, as it predicts water evaporation only at 100 °C, which contradicts experimental evidence indicating that evaporation occurs over a broader temperature range. The Wilson model significantly overestimates boiling points, reaching values up to 290 °C. Although the UNIQUAC model accurately reflects the process at higher water contents, it results in elevated energy consumption, necessitating substantial superheating of the feedstock up to 220 °C. The NRTL model provided the best correlation (among studied thermodynamic models) with experimental data, providing an average relative deviation of 3.68% and effectively capturing the two-stage evaporation mechanism: initial removal of free water at 100–110 °C, followed by bound moisture evaporation at temperatures approaching 160 °C. Vaporization rates were also examined across all models. The Peng–Robinson approach predicted the highest vaporization peaks but was the least representative of actual process conditions. Notably, in the NRTL model, the peak vaporization rates were 1.9 to 2.7 times higher than those estimated using the UNIQUAC and Wilson models. This parameter is critical for the optimal selection and design of subsequent condensation equipment. Based on these findings, the NRTL thermodynamic model is recommended for the industrial-scale implementation of thermomechanical dehydration processes involving heavy hydrocarbon feedstocks, given its accuracy in modeling phase transitions and the temperature-dependent vapor generation rates derived from sequential equilibrium flash calculations. Full article

The operational control of medium-voltage (MV) distribution networks has conventionally relied on a tightly integrated, multi-platform architecture comprising a Supervisory Control and Data Acquisition (SCADA) system, an Advanced Distribution Management System (ADMS), and a Geographic Information System (GIS), interconnected through middleware integration layers. This architecture imposes substantial capital expenditure—typically USD 3.5–4.5 million per control center deployment—and introduces structural data divergence between the ADMS operational model and the GIS geographic representation, with synchronization lags ranging from 24 h to seven days under standard batch update configurations. This paper proposes, develops, and validates a GIS-native operational control framework for MV distribution networks that eliminates the structural dependency on a standalone ADMS by embedding switching intelligence, real-time topology processing, and georeferenced operational visualization directly within the GIS platform. The framework comprises four tightly integrated components: a Unified Spatial Data Model (USDM) serving as the single authoritative network state store; an Embedded Topology Engine (ETE) implementing a loop-safe Breadth-First Search algorithm for real-time energization state computation; a Real-Time Visualization Engine (RTVE) providing continuous georeferenced display of the live network operational state; and a Switching Control Module (SCM) with a Three-State Switch Position Logic (TSPL) conflict resolution mechanism ensuring switching state integrity under concurrent RTU and operator command conditions. The framework was validated on a live operational Egyptian 11 kV distribution network comprising 312 switching elements and 42,650 customers across seven representative switching scenarios. Validation results demonstrate: zero switching state divergence (δ(t) = 0) across all 200 verification points; 100% topological correctness across all 37 switching steps; end-to-end processing latency consistently below 400 milliseconds per switching operation, representing a 14×–67× improvement over the conventional batch GIS synchronization latency; an 88–89% reduction in deployment CAPEX relative to the conventional multi-platform architecture; and a 74–75% reduction in ten-year total cost of ownership inclusive of platform licensing, custom development maintenance, and operational expenditure. The single-platform architecture additionally eliminates 100% of inter-system integration interfaces, removing the primary class of synchronization failure modes inherent to multi-platform deployments. These results establish the proposed framework as a technically rigorous and economically viable operational control solution for MV distribution utilities operating under capital-constrained conditions, with direct applicability to distribution utility sectors across Egypt, the broader MENA region, and developing-world utility environments. Full article

Traffic flow prediction is important for route planning, signal control, and traffic guidance. However, traffic-state sequences usually exhibit non-stationarity, periodicity, and complex temporal dependencies, which makes it difficult for traditional statistical methods and single deep learning models to simultaneously capture short-term local fluctuations and long-term evolutionary trends. To address this issue, this paper proposes a dual-stream latefusion CNN-LSTM with an adaptive gated shortcut for traffic flow prediction, denoted as AGS-CNN-LSTM. The proposed method does not aim at explicit spatial-topology modeling; instead, it focuses on improving the fusion mechanism of CNN-LSTM-based models under settings without graph-structure constraints. Based on two public datasets, PeMS-BAY and PeMSD8, this study constructs multi-step prediction tasks with horizons of 15 min, 30 min, 60 min, 90 min, and 120 min and compares the proposed model with MLP, SimpleRNN, 1DCNN, LSTM, Serial CNN-LSTM, CNN-LSTM-Attention, BiLSTM-Attention, TCN-LSTM, Transformer Encoder, DLinear, and DS-CNN-LSTM (w/o Gate). The experimental results show that AGS-CNN-LSTM does not consistently achieve the best performance across all datasets, prediction horizons, and evaluation metrics. Nevertheless, it performs close to the best baseline models on the 30 min and 60 min tasks of PeMS-BAY and achieves competitive RMSE and R² results on the 15 min, 30 min, and 60 min tasks of PeMSD8. Further ablation experiments indicate that the adaptive gated shortcut can enhance the predictive capability of the dual-stream late-fusion structure in some scenarios, although its benefits are dependent on the dataset and prediction horizon. Overall, the proposed model is more appropriately regarded as a lightweight fusion-mechanism improvement for CNN-LSTM-based models under settings without explicit graph-structure constraints, rather than a comprehensive replacement for complex graph neural networks, Transformerbased models, or models incorporating multiple external factors. Therefore, the findings should be interpreted as proof-of-concept evidence for a lightweight CNN-LSTM fusion enhancement under constrained non-graph-input settings, rather than as evidence of broad generalizability in complete road-network-level traffic forecasting. Full article